Theory · statistics papers, 2023–2026

Key findings

• Theory · statistics went from 16 papers in 2023 to 57 in 2026, roughly 3.6x in three years.
• NeurIPS publishes the most Theory · statistics work: 58 papers from 2023 to 2026, 42% of the four-venue total.
• The fastest-growing overlap is with Theory · learning theory: papers tagged with both rose from 1 in 2023 to 28 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #5 by 2026 paper count; the fastest grower in the group, Theory · learning theory, is up 5.6x versus 3.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Asymptotic Anytime-Valid Inference for U-statistics
• ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
• ICLR 2026The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics
• NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
• ICML 2025Contextual Bandits for Unbounded Context Distributions
• ICLR 2025Improving Pretraining Data Using Perplexity Correlations
• CVPR 2025Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics
• NeurIPS 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
• ICML 2024Neural Networks Learn Statistics of Increasing Complexity
• ICLR 2024Kernelised Normalising Flows
• NeurIPS 2023Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics
• ICML 2023Fair Densities via Boosting the Sufficient Statistics of Exponential Families
• ICLR 2023Don’t fear the unlabelled: safe semi-supervised learning via debiasing
• NeurIPS 2026Computationally sufficient statistics for Ising models
• ICML 2026Adaptive Multiscale Binary Expansion Tests for Independence
• ICLR 2026Bayesian Influence Functions for Hessian-Free Data Attribution
• NeurIPS 2025Backward Conformal Prediction
• ICML 2025Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
• ICLR 2025From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation
• NeurIPS 2024Statistical Multicriteria Benchmarking via the GSD-Front

All Theory · statistics papers

50 papers, page 1 of 1

1. ICML 2026A Random Matrix Perspective on the Consistency of Diffusion Models
2. ICML 2026A Refined Generalization Analysis for Extreme Multi-class Supervised Contrastive Representation Learning
3. ICML 2026A Studentized Spherical Harmonics–Based Nonparametric Two-Sample Test for Compositional and Directional Data
4. ICML 2026A Theory of Contrastive Learning with Natural Images
5. ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
6. ICML 2026A theory of learning data statistics in diffusion models, from easy to hard
7. ICML 2026Adaptive Multiscale Binary Expansion Tests for Independence
8. ICML 2026Approximating f -Divergences with Rank Statistics
9. ICML 2026Beyond First-order Asymptotics in Sequential Mean Testing
10. ICML 2026Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
11. ICML 2026Combinatorial Sparse PCA Beyond the Spiked Identity Model
12. ICML 2026Deep networks learn to parse uniform-depth context-free languages from local statistics
13. ICML 2026Deep Neural Network Regression with Functional Covariates
14. ICML 2026Deriving Neural Scaling Laws from the Statistics of Natural Language
15. ICML 2026Finite-Width Neural Tangent Kernels from Feynman Diagrams
16. ICML 2026Learning $U$-Statistics with Active Inference
17. ICML 2026Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing
18. ICML 2026Linear Regression with Unknown Truncation Beyond Gaussian Features
19. ICML 2026Mean-Shift PCA by Knockoff Mean
20. ICML 2026On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
21. ICML 2026On the Power of Statistics in Class-Incremental Learning with Pretrained Models
22. ICML 2026Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
23. ICML 2026Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
24. ICML 2026Provable Bounds for the Learnability of Sample-Compressible Families from Noisy Samples
25. ICML 2026Sample Complexity Bounds for Robust Mean Estimation with Mean-Shift Contamination
26. ICML 2026Sharp Concentration Bounds for Bundle-Valued Statistics on Manifolds
27. ICML 2026Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
28. ICML 2026Symmetries in language statistics shape the geometry of model representations
29. ICML 2026The Catastrophic Failure of *the* k-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It
30. ICML 2026When Softmax Fails at the Top: Extreme‑Value Corrections for InfoNCE
31. ICML 2025Batch List-Decodable Linear Regression via Higher Moments
32. ICML 2025Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
33. ICML 2025Conformal Tail Risk Control for Large Language Model Alignment
34. ICML 2025Contextual Bandits for Unbounded Context Distributions
35. ICML 2025Dimension-Independent Rates for Structured Neural Density Estimation
36. ICML 2025Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
37. ICML 2025Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
38. ICML 2025From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
39. ICML 2025On Learning Parallel Pancakes with Mostly Uniform Weights
40. ICML 2025Position: Rethinking Explainable Machine Learning as Applied Statistics
41. ICML 2025QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions
42. ICML 2025Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
43. ICML 2025The Underlying Universal Statistical Structure of Natural Datasets
44. ICML 2024DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation
45. ICML 2024Neural Networks Learn Statistics of Increasing Complexity
46. ICML 2024Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
47. ICML 2024Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
48. ICML 2024What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis
49. ICML 2023Fair Densities via Boosting the Sufficient Statistics of Exponential Families
50. ICML 2023Is Learning Summary Statistics Necessary for Likelihood-free Inference?

FAQ

How many Theory · statistics papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

138 in total: 16 in 2023, 21 in 2024, 44 in 2025, 57 in 2026.

How many Theory · statistics papers are at NeurIPS 2026?

NeurIPS 2026 has 12 Theory · statistics papers, versus 23 the year before.

How many Theory · statistics papers are at ICLR 2026?

ICLR 2026 has 15 Theory · statistics papers, versus 7 the year before.

How many Theory · statistics papers are at ICML 2026?

ICML 2026 has 30 Theory · statistics papers, versus 13 the year before.

How many Theory · statistics papers are at CVPR 2025?

CVPR 2025 has 1 Theory · statistics papers.

Which conference publishes the most Theory · statistics papers?

NeurIPS, with 58 papers from 2023 to 2026.